Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers

This paper presents a robust and efficient fault detection and diagnosis framework for handling small faults and oscillations in synchronous generator (SG) systems. The proposed framework utilizes the Brunovsky form representation of nonlinear systems to mathematically formulate the fault detection...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Pooria Ghanooni, Hamed Habibi, Amirmehdi Yazdani, Hai Wang, Somaiyeh MahmoudZadeh, Amin Mahmoudi
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	group method of data handling neural network high-gain observer L1-Norm criterion output residual generation small fault detection synchronous generator Electronics TK7800-8360
Acceso en línea:	https://doaj.org/article/01bc4b52010b4eef99938b6b9d090c77
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:01bc4b52010b4eef99938b6b9d090c77
record_format	dspace
spelling	oai:doaj.org-article:01bc4b52010b4eef99938b6b9d090c772021-11-11T15:38:55ZRapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers10.3390/electronics102126372079-9292https://doaj.org/article/01bc4b52010b4eef99938b6b9d090c772021-10-01T00:00:00Zhttps://www.mdpi.com/2079-9292/10/21/2637https://doaj.org/toc/2079-9292This paper presents a robust and efficient fault detection and diagnosis framework for handling small faults and oscillations in synchronous generator (SG) systems. The proposed framework utilizes the Brunovsky form representation of nonlinear systems to mathematically formulate the fault detection problem. A differential flatness model of SG systems is provided to meet the conditions of the Brunovsky form representation. A combination of high-gain observer and group method of data handling neural network is employed to estimate the trajectory of the system and to learn/approximate the fault- and uncertainty-associated functions. The fault detection mechanism is developed based on the output residual generation and monitoring so that any unfavorable oscillation and/or fault occurrence can be detected rapidly. Accordingly, an average L1-norm criterion is proposed for rapid decision making in faulty situations. The performance of the proposed framework is investigated for two benchmark scenarios which are actuation fault and fault impact on system dynamics. The simulation results demonstrate the capacity and effectiveness of the proposed solution for rapid fault detection and diagnosis in SG systems in practice, and thus enhancing service maintenance, protection, and life cycle of SGs.Pooria GhanooniHamed HabibiAmirmehdi YazdaniHai WangSomaiyeh MahmoudZadehAmin MahmoudiMDPI AGarticlegroup method of data handling neural networkhigh-gain observerL1-Norm criterionoutput residual generationsmall fault detectionsynchronous generatorElectronicsTK7800-8360ENElectronics, Vol 10, Iss 2637, p 2637 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	group method of data handling neural network high-gain observer L1-Norm criterion output residual generation small fault detection synchronous generator Electronics TK7800-8360
spellingShingle	group method of data handling neural network high-gain observer L1-Norm criterion output residual generation small fault detection synchronous generator Electronics TK7800-8360 Pooria Ghanooni Hamed Habibi Amirmehdi Yazdani Hai Wang Somaiyeh MahmoudZadeh Amin Mahmoudi Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
description	This paper presents a robust and efficient fault detection and diagnosis framework for handling small faults and oscillations in synchronous generator (SG) systems. The proposed framework utilizes the Brunovsky form representation of nonlinear systems to mathematically formulate the fault detection problem. A differential flatness model of SG systems is provided to meet the conditions of the Brunovsky form representation. A combination of high-gain observer and group method of data handling neural network is employed to estimate the trajectory of the system and to learn/approximate the fault- and uncertainty-associated functions. The fault detection mechanism is developed based on the output residual generation and monitoring so that any unfavorable oscillation and/or fault occurrence can be detected rapidly. Accordingly, an average L1-norm criterion is proposed for rapid decision making in faulty situations. The performance of the proposed framework is investigated for two benchmark scenarios which are actuation fault and fault impact on system dynamics. The simulation results demonstrate the capacity and effectiveness of the proposed solution for rapid fault detection and diagnosis in SG systems in practice, and thus enhancing service maintenance, protection, and life cycle of SGs.
format	article
author	Pooria Ghanooni Hamed Habibi Amirmehdi Yazdani Hai Wang Somaiyeh MahmoudZadeh Amin Mahmoudi
author_facet	Pooria Ghanooni Hamed Habibi Amirmehdi Yazdani Hai Wang Somaiyeh MahmoudZadeh Amin Mahmoudi
author_sort	Pooria Ghanooni
title	Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
title_short	Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
title_full	Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
title_fullStr	Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
title_full_unstemmed	Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers
title_sort	rapid detection of small faults and oscillations in synchronous generator systems using gmdh neural networks and high-gain observers
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/01bc4b52010b4eef99938b6b9d090c77
work_keys_str_mv	AT pooriaghanooni rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers AT hamedhabibi rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers AT amirmehdiyazdani rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers AT haiwang rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers AT somaiyehmahmoudzadeh rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers AT aminmahmoudi rapiddetectionofsmallfaultsandoscillationsinsynchronousgeneratorsystemsusinggmdhneuralnetworksandhighgainobservers
_version_	1718434646252847104

Rapid Detection of Small Faults and Oscillations in Synchronous Generator Systems Using GMDH Neural Networks and High-Gain Observers

Ejemplares similares